Discovery of Probabilistic Dirichlet-to-Neumann Maps on Graphs

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Propp, Adrienne M., Actor, Jonas A., Walker, Elise, Owhadi, Houman, Trask, Nathaniel, Tartakovsky, Daniel M.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908784185573376
author Propp, Adrienne M.
Actor, Jonas A.
Walker, Elise
Owhadi, Houman
Trask, Nathaniel
Tartakovsky, Daniel M.
author_facet Propp, Adrienne M.
Actor, Jonas A.
Walker, Elise
Owhadi, Houman
Trask, Nathaniel
Tartakovsky, Daniel M.
contents Dirichlet-to-Neumann maps enable the coupling of multiphysics simulations across computational subdomains by ensuring continuity of state variables and fluxes at artificial interfaces. We present a novel method for learning Dirichlet-to-Neumann maps on graphs using Gaussian processes, specifically for problems where the data obey a conservation constraint from an underlying partial differential equation. Our approach combines discrete exterior calculus and nonlinear optimal recovery to infer relationships between vertex and edge values. This framework yields data-driven predictions with uncertainty quantification across the entire graph, even when observations are limited to a subset of vertices and edges. By optimizing over the reproducing kernel Hilbert space norm while applying a maximum likelihood estimation penalty on kernel complexity, our method ensures that the resulting surrogate strictly enforces conservation laws without overfitting. We demonstrate our method on two representative applications: subsurface fracture networks and arterial blood flow. Our results show that the method maintains high accuracy and well-calibrated uncertainty estimates even under severe data scarcity, highlighting its potential for scientific applications where limited data and reliable uncertainty quantification are critical.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02337
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Discovery of Probabilistic Dirichlet-to-Neumann Maps on Graphs
Propp, Adrienne M.
Actor, Jonas A.
Walker, Elise
Owhadi, Houman
Trask, Nathaniel
Tartakovsky, Daniel M.
Machine Learning
Numerical Analysis
Mathematical Physics
Computational Physics
90C70, 60G15, 05C90
Dirichlet-to-Neumann maps enable the coupling of multiphysics simulations across computational subdomains by ensuring continuity of state variables and fluxes at artificial interfaces. We present a novel method for learning Dirichlet-to-Neumann maps on graphs using Gaussian processes, specifically for problems where the data obey a conservation constraint from an underlying partial differential equation. Our approach combines discrete exterior calculus and nonlinear optimal recovery to infer relationships between vertex and edge values. This framework yields data-driven predictions with uncertainty quantification across the entire graph, even when observations are limited to a subset of vertices and edges. By optimizing over the reproducing kernel Hilbert space norm while applying a maximum likelihood estimation penalty on kernel complexity, our method ensures that the resulting surrogate strictly enforces conservation laws without overfitting. We demonstrate our method on two representative applications: subsurface fracture networks and arterial blood flow. Our results show that the method maintains high accuracy and well-calibrated uncertainty estimates even under severe data scarcity, highlighting its potential for scientific applications where limited data and reliable uncertainty quantification are critical.
title Discovery of Probabilistic Dirichlet-to-Neumann Maps on Graphs
topic Machine Learning
Numerical Analysis
Mathematical Physics
Computational Physics
90C70, 60G15, 05C90
url https://arxiv.org/abs/2506.02337